guhao

marcusguhao's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated 2 models 9 days ago

marcusguhao/IndexMem-Qwen3-4B

Updated 9 days ago

marcusguhao/IndexMem-Qwen3-8B

Updated 9 days ago

upvoted 3 papers about 1 month ago

TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models

Paper • 2610.07767 • Published Oct 6 • 44

Periodic Weak Spots: Phase Sensitivity from Chunked KV-Cache Compression

Paper • 2609.36322 • Published Sep 28 • 36

TRIAGE: Direction-Aware Mismatch Stabilization of Native NVFP4 Reinforcement Learning

Paper • 2610.07043 • Published Oct 5 • 36

upvoted 3 papers about 2 months ago

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

Paper • 2609.19969 • Published Sep 17 • 208

Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation

Paper • 2609.11638 • Published Sep 10 • 223

Block Sparse Attention with Log-Linear Complexity

Paper • 2609.31093 • Published Sep 25 • 29

updated a collection about 2 months ago

IndexMem++

Collection

Learned KV-cache eviction gates for Qwen3, from "The Gating Mechanism of KV Cache Eviction". • 2 items • Updated 9 days ago

published a model about 2 months ago

marcusguhao/IndexMem-Qwen3-4B

Updated 9 days ago

updated a collection about 2 months ago

IndexMem++

Collection

Learned KV-cache eviction gates for Qwen3, from "The Gating Mechanism of KV Cache Eviction". • 2 items • Updated 9 days ago

published a model about 2 months ago

marcusguhao/IndexMem-Qwen3-8B

Updated 9 days ago

upvoted 3 papers 2 months ago

SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking

Paper • 2609.13141 • Published Sep 11 • 67

PARSER: Read in Parallel, Reason in Depth for Long-Context LLM Agents

Paper • 2609.06702 • Published Sep 6 • 22

T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks

Paper • 2609.11042 • Published Sep 10 • 65

updated a collection 3 months ago

IndexMem++

Collection

Learned KV-cache eviction gates for Qwen3, from "The Gating Mechanism of KV Cache Eviction". • 2 items • Updated 9 days ago

upvoted a paper 4 months ago

IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse

Paper • 2603.12201 • Published Mar 12 • 68

authored 2 papers 4 months ago

Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling

Paper • 2607.02980 • Published Jul 3 • 82

IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM Inference

Paper • 2605.25475 • Published May 25